Chart Question Answering: State of the Art and Future Directions

Abstract

Information visualizations such as bar charts and line charts are very common for analyzing data and discovering critical insights. Often people analyze charts to answer questions that they have in mind. Answering such questions can be challenging as they often require a significant amount of perceptual and cognitive effort. Chart Question Answering (CQA) systems typically take a chart and a natural language question as input and automatically generate the answer to facilitate visual data analysis. Over the last few years, there has been a growing body of literature on the task of CQA. In this survey, we systematically review the current state-of-the-art research focusing on the problem of chart question answering. We provide a taxonomy by identifying several important dimensions of the problem domain including possible inputs and outputs of the task and discuss the advantages and limitations of proposed solutions. We then summarize various evaluation techniques used in the surveyed papers. Finally, we outline the open challenges and future research opportunities related to chart question answering. CCS Concepts• Human-centered computing → Visualization; • Computing methodologies → Natural language processing; Automatic chart question answering is a challenging task because of the richness and ambiguities of natural language and complex reasoning that may be required to predict the answer [SBT * 16]. The problem is also very inter-disciplinary in nature, falling in the intersection of information visualization, natural language processing, and human computer interactions. Some early approaches on NLIs and chart question answering applied natural language processing techniques by largely depending on heuristics or grammar-based parsing techniques [SBT * 16, SS18, HSTD17, GDA * 15]. Recently, there have been also some attempts for applying deep learning models for understanding natural language

Chatbot-Based Natural Language Interfaces for Data Visualisation: A Scoping Review

“…Srinivasan et al [11] proposed three task-based categories: visualisation-related tasks, data-related tasks and system-control-related tasks. Moreover, a recent systematic review [22] analysed NLIs both for databases and for data visualisations in terms of input and output. On the input side, they examined multimodality and different types of queries, such as open-ended or factual.…”